Modeling filled pauses in medical dictations

Authors:
Sergey V. Pakhomov
Affiliations:
University of Minnesota, Minneapolis, MN
Venue:
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Year:
1999

Citing 0
Cited 6

Error Analysis of Automatic Speech Recognition Using Principal Direction Divisive Partitioning

ECML '00 Proceedings of the 11th European Conference on Machine Learning
Generating training data for medical dictations

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Domain-specific language models and lexicons for tagging

Journal of Biomedical Informatics
Measures of semantic similarity and relatedness in the biomedical domain

Journal of Biomedical Informatics
Production of filled pauses in concatenative speech synthesis based on the underlying fluent sentence

Speech Communication
Linking uncertainty in physicians' narratives to diagnostic correctness

ExProM '12 Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Filled pauses are characteristic of spontaneous speech and can present considerable problems for speech recognition by being often recognized as short words. An um can be recognized as thumb or arm if the recognizer's language model does not adequately represent FP's. Recognition of quasi-spontaneous speech (medical dictation) is subject to this problem as well. Results from medical dictations by 21 family practice physicians show that using an FP model trained on the corpus populated with FP's produces overall better result than a model trained on a corpus that excluded FP's or a corpus that had random FP's.